© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33552
    Prev
    Next
    INDEX
    Explanations

    Baghdad come, Apple partly, human pulmonary, baby worth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ework
    -0.07
    дей
    -0.07
    è¿ijä¹İ
    -0.07
     abwechsl
    -0.07
    utre
    -0.07
    Reality
    -0.06
     completely
    -0.06
     insisti
    -0.06
    SWG
    -0.06
    än
    -0.06
    POSITIVE LOGITS
     rac
    0.07
    缸åħ³éĹ®çŃĶ
    0.07
    ért
    0.07
    ιβ
    0.07
    èĿ
    0.07
    éģĵéķ¿
    0.06
     ìĹŃ
    0.06
    ftar
    0.06
    .slim
    0.06
    Òĵ
    0.06
    Activations Density 0.031%

    No Known Activations